Orihime 12B by yamatazen

 ยป  All LLMs  ยป  yamatazen  ยป  Orihime 12B   URL Share it on

  Merged Model   Autotrain compatible Base model:elizezen/himeyuri-v... Base model:shisa-ai/shisa-v2-m...   Chatml   Conversational   En   Endpoints compatible   Ja   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/yamatazen/Orihime-12B 

Orihime 12B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Orihime 12B (yamatazen/Orihime-12B)
๐ŸŒŸ Advertise your project ๐Ÿš€

Orihime 12B Parameters and Internals

LLM NameOrihime 12B
Repository ๐Ÿค—https://huggingface.co/yamatazen/Orihime-12B 
Base Model(s)  Elizezen/Himeyuri-v0.1-12B   Shisa V2 Mistral Nemo 12B   Elizezen/Himeyuri-v0.1-12B   shisa-ai/shisa-v2-mistral-nemo-12b
Merged ModelYes
Model Size12b
Required VRAM23.8 GB
Updated2025-09-23
Maintaineryamatazen
Model Typemistral
Model Files  1.3 GB: 1-of-25   1.3 GB: 2-of-25   1.0 GB: 3-of-25   0.9 GB: 4-of-25   0.9 GB: 5-of-25   0.9 GB: 6-of-25   1.0 GB: 7-of-25   0.9 GB: 8-of-25   0.9 GB: 9-of-25   0.9 GB: 10-of-25   1.0 GB: 11-of-25   0.9 GB: 12-of-25   0.9 GB: 13-of-25   0.9 GB: 14-of-25   1.0 GB: 15-of-25   0.9 GB: 16-of-25   0.9 GB: 17-of-25   0.9 GB: 18-of-25   1.0 GB: 19-of-25   0.9 GB: 20-of-25   0.9 GB: 21-of-25   0.9 GB: 22-of-25   1.0 GB: 23-of-25   0.9 GB: 24-of-25   0.8 GB: 25-of-25
Supported Languagesen ja
Model ArchitectureMistralForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.51.3
Tokenizer ClassPreTrainedTokenizer
Padding Token<pad>
Vocabulary Size131074
Torch Data Typebfloat16

Best Alternatives to Orihime 12B

Best Alternatives
Context / RAM
Downloads
Likes
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB261349132
MN 12B Mag Mell R11000K / 24.5 GB64075201
Impish Nemo 12B1000K / 24.5 GB212743
KansenSakura Radiance RP 12B1000K / 24.5 GB53511
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB4755522
Irix Mpf Stock1000K / 24.5 GB2082
Captain Eris Violet V0.420 12B1000K / 24.5 GB200354
Captain Eris BMO Violent 12B1000K / 24.5 GB3052
Dans SakuraKaze V1.0.0 12B1000K / 24.5 GB6719
...n Eris BMO Violent GRPO V0.4201000K / 24.5 GB923
Note: green Score (e.g. "73.2") means that the model is better than yamatazen/Orihime-12B.

Rank the Orihime 12B Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51534 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124